Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4011 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.4495. Min Act: -0.0000

Data Index: 130588 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1327646 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.4631. Min Act: -0.0000

Data Index: 976906 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2571. Min Act: -0.0000

Data Index: 610344 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2254. Min Act: -0.0000

Data Index: 472104 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1208937 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1723. Min Act: -0.0000

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2091. Min Act: -0.0000

Data Index: 169274 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.2799. Min Act: -0.0000

Data Index: 181951 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1861. Min Act: -0.0000

Data Index: 488999 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1930. Min Act: -0.0000

Data Index: 730287 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1429. Min Act: -0.0000

Data Index: 790857 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1379337 (Python Code)

Max Activating Token Index: 658

Text #13

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1000217 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1386. Min Act: -0.0000

Data Index: 890992 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1032387 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1229777 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1464. Min Act: -0.0000

Data Index: 346346 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1387. Min Act: -0.0000

Data Index: 710843 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.4631. Min Range: -1.4631

Max Act: 1.1571. Min Act: -0.0000

Data Index: 519989 (C4 (Web Text))

Max Activating Token Index: 66